{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G5JZFB2ITABFM6GJLRHWYLCVI3","short_pith_number":"pith:G5JZFB2I","schema_version":"1.0","canonical_sha256":"375392874898025678c95c4f6c2c5546f2c68fc058d9837c2075935f21f88e16","source":{"kind":"arxiv","id":"1803.06978","version":4},"attestation_state":"computed","paper":{"title":"Improving Transferability of Adversarial Examples with Input Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Jianyu Wang, Song Bai, Yuyin Zhou, Zhishuai Zhang, Zhou Ren","submitted_at":"2018-03-19T15:07:51Z","abstract_excerpt":"Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing adversarial attacks only achieve relatively low success rates under the challenging black-box setting, where the attackers have no knowledge of the model structure and parameters. To this end, we propose to improve the transferability of adversarial examples by creating diverse input patterns. Instead of only using the original images to generate adversarial examples"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1803.06978","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-19T15:07:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"cbc570b1635c33df78e4454f310f066faa06c8097d4271289648b8cf63c84fc8","abstract_canon_sha256":"4e6df736de755e6c228768c9a3078a1a89b38bd88d05aa7501b2540e8e2add65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:32.673979Z","signature_b64":"IWct/O4eAR0PIR6dzKW41Euh62CN0D7ya2LiQyM/6y2adv1OOYUOpUEqTwFLa1wKjRD8y9JEhRH2RC+aMyVeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375392874898025678c95c4f6c2c5546f2c68fc058d9837c2075935f21f88e16","last_reissued_at":"2026-05-17T23:44:32.673246Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:32.673246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Transferability of Adversarial Examples with Input Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Jianyu Wang, Song Bai, Yuyin Zhou, Zhishuai Zhang, Zhou Ren","submitted_at":"2018-03-19T15:07:51Z","abstract_excerpt":"Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing adversarial attacks only achieve relatively low success rates under the challenging black-box setting, where the attackers have no knowledge of the model structure and parameters. To this end, we propose to improve the transferability of adversarial examples by creating diverse input patterns. Instead of only using the original images to generate adversarial examples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06978","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.06978","created_at":"2026-05-17T23:44:32.673383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06978v4","created_at":"2026-05-17T23:44:32.673383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06978","created_at":"2026-05-17T23:44:32.673383+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5JZFB2ITABF","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5JZFB2ITABFM6GJ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5JZFB2I","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3","json":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3.json","graph_json":"https://pith.science/api/pith-number/G5JZFB2ITABFM6GJLRHWYLCVI3/graph.json","events_json":"https://pith.science/api/pith-number/G5JZFB2ITABFM6GJLRHWYLCVI3/events.json","paper":"https://pith.science/paper/G5JZFB2I"},"agent_actions":{"view_html":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3","download_json":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3.json","view_paper":"https://pith.science/paper/G5JZFB2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06978&json=true","fetch_graph":"https://pith.science/api/pith-number/G5JZFB2ITABFM6GJLRHWYLCVI3/graph.json","fetch_events":"https://pith.science/api/pith-number/G5JZFB2ITABFM6GJLRHWYLCVI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3/action/storage_attestation","attest_author":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3/action/author_attestation","sign_citation":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3/action/citation_signature","submit_replication":"https://pith.science/pith/G5JZFB2ITABFM6GJLRHWYLCVI3/action/replication_record"}},"created_at":"2026-05-17T23:44:32.673383+00:00","updated_at":"2026-05-17T23:44:32.673383+00:00"}